Obstacle avoidance and navigation in the real world by a seeing robot rover

By Hans P. Moravec. 1980

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

The AdobeIndoorNav Dataset: Towards Deep Reinforcement Learning based Real-world Indoor Robot Visual Navigation (2018, background): “Robot visual navigation has a long history [15], [16], [17], [18], [19].”
Perceptual Image Hashing Via Feature Points: Performance Evaluation and Tradeoffs (2006, methodology): “The construction of the detector is based on a corner detection created by Moravec [20].”
Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion (2011, methodology): “The Harris corner detector modifies the Moravec interest operator [ 85 ] by using a first order derivative approximation to the second derivative.”
Monocular Omnidirectional Visual Odometry for Outdoor Ground Vehicles (2008, background): “Most of the work in estimating robot motion has been produced using stereo cameras and can be traced back to Moravec’s work [1].”
Faster and Better: A Machine Learning Approach to Corner Detection (2008, background): “Since real images are used, there is no good definition of ground truth, so a number of human test subjects (e.g. 10) familiar with corner detection in general, but notthe methods under test, label corners in the test images.”
Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications (2012, background): “Early research in VO is opted for the former approach [2]–[5] while the works in the last decade concentrated on the latter approach [1], [6]–[9].”
Visual teach and repeat for long‐range rover autonomy (2010, methodology): “Throughout this work, we use a generic localization module based on the stereo VO algorithm pioneered by Moravec (1980) and refined by Matthies (1989) and others .”
Visual odometry for ground vehicle applications (2006, background): “Work on estimating robot motion with stereo cameras goes back at least to Moravec's work at Stanford in the 1970s (Moravec 1980).”
Toward Reliable Off Road Autonomous Vehicles Operating in Challenging Environments (2006, background): “One of the earliest autonomous mobile robots was the Stanford Cart which, in 1978, spent more time thinking than moving (Moravec 1980) in a very structured environment.”
Machine Learning for High-Speed Corner Detection (2006, background): “Moravec [4] computes the sum-of-squared-differences (SSD) between a patch around a candidate corner and patches shifted a small distance in a number of directions.”
Geometrically invariant watermarking using feature points (2002, methodology): “The construction of the detector is based on a corner detection function created by Moravec [32].”
Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking (2011, methodology): “Corner Detectors Corners are among the first low-level features used for image analysis and in particular, tracking (Moravec 1980).”
An Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics (2015, background): “The problem of estimating a robot’s ego-motion by observing a sequence of images started in the 1980s by Moravec [82] at Stanford University.”
Good features to track (1994, background): “Feature windows can be selected based on some measure of texturedness or cornerness, such as a high standard deviation in the spatial intensity pro le [13], the presence of zero crossings of the Laplacian of the image intensity [12], and corners [9], [5].”
Two years of Visual Odometry on the Mars Exploration Rovers (2007, background): “Work on estimating robot motion with stereo cameras can be traced back to Moravec’s work (Moravec, 1980).”
Behavioral dynamics of steering, obstacle avoidance, and route selection. (2003, unknown): “A common approach to path planning is model-based control, which is characterized in robotics by a “ sense-model-plan-act” scheme (Brooks, 1991; Moravec, 1981 ).”